{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L3HXCROWLPZPHQ5XZ2Y4CGZAK7","short_pith_number":"pith:L3HXCROW","schema_version":"1.0","canonical_sha256":"5ecf7145d65bf2f3c3b7ceb1c11b2057c3414146845d6a7a328c0658e3e3277b","source":{"kind":"arxiv","id":"1807.06638","version":1},"attestation_state":"computed","paper":{"title":"Developing a Portable Natural Language Processing Based Phenotyping System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chengsheng Mao, Guoqian Jiang, Haleh Vatani, Himanshu Sharma, Jyotishman Pathak, Liang Yao, Luke Rasmussen, Yizhen Zhang, Yizhen Zhong, Yuan Luo","submitted_at":"2018-07-17T19:40:28Z","abstract_excerpt":"This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating OHDSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.06638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-17T19:40:28Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3908e13d74aecd32fcf2ffc441f910249a53dde52f6cfad61e0f22addaccfdcb","abstract_canon_sha256":"cd997ccc1667e984a3a78d7ef6779456458fa1b8acb17bc17546717667a06415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:27.314698Z","signature_b64":"F1jwh5T7q6zO9bRgv5wWVaf5A3ChCYqrUXi42hTAu5cbRAwzsbrTfi+NlVmr6CwK0O/x3KIrfm1mJXgRgxS9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ecf7145d65bf2f3c3b7ceb1c11b2057c3414146845d6a7a328c0658e3e3277b","last_reissued_at":"2026-05-18T00:10:27.314135Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:27.314135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developing a Portable Natural Language Processing Based Phenotyping System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chengsheng Mao, Guoqian Jiang, Haleh Vatani, Himanshu Sharma, Jyotishman Pathak, Liang Yao, Luke Rasmussen, Yizhen Zhang, Yizhen Zhong, Yuan Luo","submitted_at":"2018-07-17T19:40:28Z","abstract_excerpt":"This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating OHDSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06638","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.06638","created_at":"2026-05-18T00:10:27.314215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06638v1","created_at":"2026-05-18T00:10:27.314215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06638","created_at":"2026-05-18T00:10:27.314215+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3HXCROWLPZP","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3HXCROWLPZPHQ5X","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3HXCROW","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7","json":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7.json","graph_json":"https://pith.science/api/pith-number/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/graph.json","events_json":"https://pith.science/api/pith-number/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/events.json","paper":"https://pith.science/paper/L3HXCROW"},"agent_actions":{"view_html":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7","download_json":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7.json","view_paper":"https://pith.science/paper/L3HXCROW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06638&json=true","fetch_graph":"https://pith.science/api/pith-number/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/graph.json","fetch_events":"https://pith.science/api/pith-number/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/action/storage_attestation","attest_author":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/action/author_attestation","sign_citation":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/action/citation_signature","submit_replication":"https://pith.science/pith/L3HXCROWLPZPHQ5XZ2Y4CGZAK7/action/replication_record"}},"created_at":"2026-05-18T00:10:27.314215+00:00","updated_at":"2026-05-18T00:10:27.314215+00:00"}